Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2459 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4624. Min Act: -0.0001

Data Index: 1419922 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4772. Min Act: -0.0001

Data Index: 464147 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4158. Min Act: -0.0001

Data Index: 1380407 (Python Code)

Max Activating Token Index: 355

Text #3

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3567. Min Act: -0.0001

Data Index: 1129113 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1447324 (Python Code)

Max Activating Token Index: 419

Text #5

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1298846 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1593410 (Python Code)

Max Activating Token Index: 831

Text #7

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3908. Min Act: -0.0001

Data Index: 1508526 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3912. Min Act: -0.0001

Data Index: 1425278 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3845. Min Act: -0.0001

Data Index: 402159 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3853. Min Act: -0.0001

Data Index: 1535970 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3434. Min Act: -0.0001

Data Index: 471965 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3827. Min Act: -0.0001

Data Index: 1519440 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3672. Min Act: -0.0001

Data Index: 1514342 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3405. Min Act: -0.0001

Data Index: 1450676 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1595137 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3849. Min Act: -0.0001

Data Index: 663931 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3639. Min Act: -0.0001

Data Index: 1387467 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1563182 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.4772. Min Range: -0.4772

Max Act: 0.3545. Min Act: -0.0001

Data Index: 1362805 (Python Code)

Max Activating Token Index: 251